A Comparative Study of Ensemble Methods for Prediction of Surface Settlement Induced by TBM Tunneling

Tatiana Richa; Selmane Lebdaoui; Jean Michel Pereira; Gilles Chapron; Lina María Guayacán-Carrillo

doi:10.1061/9780784484975.023

A Comparative Study of Ensemble Methods for Prediction of Surface Settlement Induced by TBM Tunneling

Tatiana Richa
, Selmane Lebdaoui
, Jean Michel Pereira
, Gilles Chapron
, Lina María Guayacán-Carrillo

Terrasol Setec
Université Paris Est, ENPC LIGM, IMAGINE

Résultats de recherche: Contribution à un journal › Article de conférence › Revue par des pairs

Résumé

The purpose of this study is to apply ensemble methods to predict surface settlement induced by earth pressure balance tunnel boring machine. Random forest (RF) and Extreme Gradient Boosting (XGBoost) algorithms are applied on 1,101 settlement measurements collected from the Grand Paris Express project. The results are compared with the performance of the back-propagation artificial neural networks (BPNN). Finally, the results show that both ensemble methods XGBoost and RF are better than BPNN based on R² and RMSE indicators.

langue originale	Anglais
Pages (de - à)	211-219
Nombre de pages	9
journal	Geotechnical Special Publication
Volume	2023-July
Numéro de publication	GSP 345
Les DOIs	https://doi.org/10.1061/9780784484975.023
état	Publié - 1 janv. 2023
Evénement	Geo-Risk Conference 2023: Innovation in Data and Analysis Methods - Arlington, États-Unis Durée: 23 juil. 2023 → 26 juil. 2023

Accès au document

10.1061/9780784484975.023

Autres fichiers et liens

Lien vers la publication dans Scopus

Contient cette citation

@article{2c599a202582405eb358befe308caeeb,

title = "A Comparative Study of Ensemble Methods for Prediction of Surface Settlement Induced by TBM Tunneling",

abstract = "The purpose of this study is to apply ensemble methods to predict surface settlement induced by earth pressure balance tunnel boring machine. Random forest (RF) and Extreme Gradient Boosting (XGBoost) algorithms are applied on 1,101 settlement measurements collected from the Grand Paris Express project. The results are compared with the performance of the back-propagation artificial neural networks (BPNN). Finally, the results show that both ensemble methods XGBoost and RF are better than BPNN based on R2 and RMSE indicators.",

author = "Tatiana Richa and Selmane Lebdaoui and Pereira, \{Jean Michel\} and Gilles Chapron and Guayac{\'a}n-Carrillo, \{Lina Mar{\'i}a\}",

note = "Publisher Copyright: {\textcopyright} 2023 American Society of Civil Engineers (ASCE). All rights reserved.; Geo-Risk Conference 2023: Innovation in Data and Analysis Methods ; Conference date: 23-07-2023 Through 26-07-2023",

year = "2023",

month = jan,

day = "1",

doi = "10.1061/9780784484975.023",

language = "English",

volume = "2023-July",

pages = "211--219",

journal = "Geotechnical Special Publication",

issn = "0895-0563",

number = "GSP 345",

}

TY - JOUR

T1 - A Comparative Study of Ensemble Methods for Prediction of Surface Settlement Induced by TBM Tunneling

AU - Richa, Tatiana

AU - Lebdaoui, Selmane

AU - Pereira, Jean Michel

AU - Chapron, Gilles

AU - Guayacán-Carrillo, Lina María

PY - 2023/1/1

Y1 - 2023/1/1

N2 - The purpose of this study is to apply ensemble methods to predict surface settlement induced by earth pressure balance tunnel boring machine. Random forest (RF) and Extreme Gradient Boosting (XGBoost) algorithms are applied on 1,101 settlement measurements collected from the Grand Paris Express project. The results are compared with the performance of the back-propagation artificial neural networks (BPNN). Finally, the results show that both ensemble methods XGBoost and RF are better than BPNN based on R2 and RMSE indicators.

AB - The purpose of this study is to apply ensemble methods to predict surface settlement induced by earth pressure balance tunnel boring machine. Random forest (RF) and Extreme Gradient Boosting (XGBoost) algorithms are applied on 1,101 settlement measurements collected from the Grand Paris Express project. The results are compared with the performance of the back-propagation artificial neural networks (BPNN). Finally, the results show that both ensemble methods XGBoost and RF are better than BPNN based on R2 and RMSE indicators.

UR - https://www.scopus.com/pages/publications/85184372183

U2 - 10.1061/9780784484975.023

DO - 10.1061/9780784484975.023

M3 - Conference article

AN - SCOPUS:85184372183

SN - 0895-0563

VL - 2023-July

SP - 211

EP - 219

JO - Geotechnical Special Publication

JF - Geotechnical Special Publication

IS - GSP 345

T2 - Geo-Risk Conference 2023: Innovation in Data and Analysis Methods

Y2 - 23 July 2023 through 26 July 2023

ER -

A Comparative Study of Ensemble Methods for Prediction of Surface Settlement Induced by TBM Tunneling

Résumé

Accès au document

Autres fichiers et liens

Empreinte digitale

Contient cette citation